公开(公告)号：US11315567B2

公开(公告)日：2022-04-26

申请号：US16872664

申请日：2020-05-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sang Hyun Yoo ,  Young-Seok Kim ,  Jeong-Hoon Park ,  Jehun Jeon ,  Junhwi Choi

IPC: G10L15/22 ,  G10L15/18 ,  G06F3/16 ,  G10L15/08 ,  G06F3/0484

Abstract: An electronic device and an method of the electronic device are provided, where the electronic device maintains a context that does not reflect a request for a secret conversation, in response to the request for the secret conversation being received from a first user, and generates a response signal to a voice signal of a second user based on the maintained context, in response to an end of the secret conversation with the first user.

公开(公告)号：US10685653B2

公开(公告)日：2020-06-16

申请号：US15992412

申请日：2018-05-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sang Hyun Yoo ,  Young-Seok Kim ,  Jeong-hoon Park ,  Jehun Jeon ,  Junhwi Choi

IPC: G10L15/22 ,  G10L15/18 ,  G06F3/16 ,  G10L15/08 ,  G06F3/0484

Abstract: An electronic device and an method of the electronic device are provided, where the electronic device maintains a context that does not reflect a request for a secret conversation, in response to the request for the secret conversation being received from a first user, and generates a response signal to a voice signal of a second user based on the maintained context, in response to an end of the secret conversation with the first user.

公开(公告)号：US10546574B2

公开(公告)日：2020-01-28

申请号：US15686913

申请日：2017-08-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jung-Hoe Kim ,  Jehun Jeon ,  Kyoung Gu Woo

IPC: G10L15/02 ,  G10L15/22 ,  G10L15/14 ,  G10L15/18

Abstract: A voice recognition apparatus and corresponding method include a processor configured to calculate a probability distribution corresponding to an intent associated with an utterance of a user by applying pre-stored training data to an input voice signal input based on the utterance. The processor is also configured to select a target feature extractor including either one or both of a training-based feature extractor and a rule-based feature extractor using the calculated probability distribution, and extract a feature associated with the utterance based on the selected target feature extractor.

公开(公告)号：US12020136B2

公开(公告)日：2024-06-25

申请号：US16292545

申请日：2019-03-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junhwi Choi ,  Young-Seok Kim ,  Jeong-Hoon Park ,  Seongmin Ok ,  Jehun Jeon

IPC: G06N3/045 ,  G06N3/048 ,  G06N3/084 ,  G06V20/58 ,  G10L15/16

CPC classification number: G06N3/045 ,  G06N3/048 ,  G06N3/084 ,  G06V20/584 ,  G10L15/16

Abstract: Disclosed is an operation method of a neural network including a first network and a second network, the method including acquiring state information output from the first network based on input information, determining whether the state information satisfies a condition using the second network, iteratively applying the state information to the first network in response to determining that the state information does not satisfy the condition, and outputting the state information in response to determining that the state information satisfy the condition.

公开(公告)号：US11295729B2

公开(公告)日：2022-04-05

申请号：US16829180

申请日：2020-03-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jehun Jeon ,  Misuk Kim ,  Jeong-Hoon Park ,  GyuBum Han

IPC: G10L15/16 ,  G06F17/18 ,  G06N3/04 ,  G06N3/08 ,  G10L15/06 ,  G10L15/22 ,  G10L19/00

Abstract: A processor-implemented response inference method and apparatus are disclosed. The response inference apparatus receives an input, generates a latent variable vector in a latent variable region space by encoding the input, generates a validation vector with a predetermined phase difference from the latent variable vector, generates an output response by decoding the latent variable vector, generates a validation response by decoding the validation vector, and validates the output response by comparing the output response to the validation response.

公开(公告)号：US10733975B2

公开(公告)日：2020-08-04

申请号：US15913486

申请日：2018-03-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Young-Seok Kim ,  Sang Hyun Yoo ,  Jehun Jeon ,  Junhwi Choi

IPC: G10L15/00 ,  G10L15/065 ,  G10L15/06 ,  G10L15/22 ,  G10L15/18 ,  G06F16/33 ,  G06N3/04 ,  G06N3/08 ,  G06F40/30 ,  G06F40/56 ,  G10L15/16

Abstract: An out-of-service (OOS) sentence generating method includes: training models based on a target utterance template of a target service and a target sentence generated from the target utterance template; generating a similar utterance template that is similar to the target utterance template based on a trained model, among the trained models, and a sentence generated from an utterance template of another service; and generating a similar sentence that is similar to the target sentence based on another trained model, among the trained models, and the similar utterance template.

公开(公告)号：US11580963B2

公开(公告)日：2023-02-14

申请号：US17069927

申请日：2020-10-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jangsu Lee ,  Hoshik Lee ,  Jehun Jeon

IPC: G10L13/07 ,  G10L15/18 ,  G10L15/16 ,  G10L13/027 ,  G10L15/02 ,  G10L15/08

Abstract: A speech generation method and apparatus are disclosed. The speech generation method includes obtaining, by a processor, a linguistic feature and a prosodic feature from an input text, determining, by the processor, a first candidate speech element through a cost calculation and a Viterbi search based on the linguistic feature and the prosodic feature, generating, at a speech element generator implemented at the processor, a second candidate speech element based on the linguistic feature or the prosodic feature and the first candidate speech element, and outputting, by the processor, an output speech by concatenating the second candidate speech element and a speech sequence determined through the Viterbi search.

公开(公告)号：US11487953B2

公开(公告)日：2022-11-01

申请号：US16872723

申请日：2020-05-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Misuk Kim ,  Sanghyun Yoo ,  Jeong-Hoon Park ,  Jehun Jeon ,  GyuBum Han

IPC: G06F40/56 ,  G06F40/268 ,  G06F40/205 ,  G06F40/30 ,  G10L15/18 ,  H04L51/02 ,  G06F16/9032 ,  G06F16/332 ,  G06F16/33

Abstract: A method and apparatus with natural language processing is disclosed. The method includes determining a first similarity between an input sentence of a user and a select first database query sentence and dependent on a determination that the first similarity fails to meet a first threshold, determining a second similarity between a portion of the input sentence, less than all of the input sentence, and a select second database query sentence, and in response to the second similarity meeting a second threshold, outputting a response sentence corresponding to the second database query sentence as a response to the input sentence.

公开(公告)号：US20200273460A1

公开(公告)日：2020-08-27

申请号：US16872664

申请日：2020-05-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sang Hyun Yoo ,  Young-Seok Kim ,  Jeong-hoon Park ,  Jehun Jeon ,  Junhwi Choi

IPC: G10L15/22 ,  G10L15/18 ,  G06F3/16

Abstract: An electronic device and an method of the electronic device are provided, where the electronic device maintains a context that does not reflect a request for a secret conversation, in response to the request for the secret conversation being received from a first user, and generates a response signal to a voice signal of a second user based on the maintained context, in response to an end of the secret conversation with the first user.

公开(公告)号：US12039277B2

公开(公告)日：2024-07-16

申请号：US17186830

申请日：2021-02-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Inkyu Choi ,  Jehun Jeon ,  GyuBum Han

IPC: G06F17/00 ,  G06F40/30 ,  G06N3/08 ,  G06N5/02

CPC classification number: G06F40/30 ,  G06N3/08 ,  G06N5/02

Abstract: A method and device with natural language processing is disclosed. The method includes performing a word embedding of an input sentence, encoding a result of the word embedding, using an encoder of a natural language processing model, to generate a context embedding vector, decoding the context embedding vector, using a decoder of the natural language processing model, to generate an output sentence corresponding to the input sentence, generating a score indicating a relationship between the context embedding vector and each of a plurality of knowledge embedding vectors, determining a first loss based on the output sentence, determining a second loss based on the generated score, and performing training of the natural language processing model, including training the natural language processing model based on the determined first loss, and training the natural language processing model based on the determined second loss.